GEE支持下联合植被物候特征与机器学习的入侵植物互花米草提取

doi:10.13474/j.cnki.11-2246.2023.0165

测绘通报 ›› 2023, Vol. 0 ›› Issue (6): 36-43.doi: 10.13474/j.cnki.11-2246.2023.0165

GEE支持下联合植被物候特征与机器学习的入侵植物互花米草提取

刘明月^1,2,3,4, 郑浩^1,2, 陈星彤¹, 杨晓芜^1,2, 宋敬茹^1,2, 张永彬¹, 满卫东^1,2,3,4

1. 华北理工大学矿业工程学院, 河北唐山 063210;
2. 唐山市资源与环境遥感重点实验室, 河北唐山 063210;
3. 河北省矿区生态修复产业技术研究院, 河北唐山 063210;
4. 矿产资源绿色开发与生态修复协同创新中心, 河北唐山 063210

收稿日期:2022-08-23 发布日期:2023-07-05
通讯作者: 满卫东。E-mail:manwd@ncst.edu.cn
作者简介:刘明月(1988-),女,博士,副教授,研究方向为滨海湿地生态遥感、入侵植物遥感监测。E-mail:liumy917@ncst.edu.cn
基金资助:
国家自然科学基金青年基金(41901375;42101393);河北省自然科学基金青年基金(D2019209322;D2022209005);河北省高等学校科学技术研究项目青年拔尖人才项目(BJ2020058);河北省引进留学人员资助项目(C20200103);唐山市科技计划重点研发项目(22150221J)

Extraction of invasive plant Spartina alterniflora by combining vegetation phenological characteristics and machine learning supported by GEE

LIU Mingyue^1,2,3,4, ZHENG Hao^1,2, CHEN Xingtong¹, YANG Xiaowu^1,2, SONG Jingru^1,2, ZHANG Yongbin¹, MAN Weidong^1,2,3,4

1. College of Mining Engineering, North China University of Science and Technology, Tangshan 063210, China;
2. Tangshan Key Laboratory of Resources and Environmental Remote Sensing, Tangshan 063210, China;
3. Hebei Industrial Technology Institute of Mine Ecological Remediation, Tangshan 063210, China;
4. Collaborative Innovation Center of Green Development and Ecological Restoration of Mineral Resources, Tangshan 063210, China

Received:2022-08-23 Published:2023-07-05

摘要/Abstract

摘要： 外来物种入侵威胁生物多样性,破坏生态系统的结构与功能。互花米草作为我国首批16种外来入侵物种名单中唯一的海岸盐沼植物,对其实现快速精准的识别对滨海湿地可持续发展与管理具有重要意义。本文基于GEE密集时序Sentinel-2影像,利用HANTS算法拟合NDVI时序曲线,采用J-M距离优选互花米草识别关键物候期,综合关键物候期Sentinel-1雷达、Sentinel-2光学影像与DEM数据,构建光谱、雷达、地形、纹理特征集,分别采用支持向量机(SVM)、分类回归树(CART)、随机森林(RF)和梯度提升树(GTB)4种方法实现盐城滨海湿地互花米草信息提取。研究表明:①基于HANTS算法与J-M距离优选的互花米草识别关键物候期为成熟期和衰老初期(10—11月),关键物候期内互花米草与土著植物的可分离性显著提高;②利用关键物候期内多源特征集训练SVM、CART、RF与GTB分类器,互花米草F1值分别为0.95、0.93、0.97、0.95,RF分类效果最优;③盐城湿地珍禽国家级自然保护区核心区现有互花米草面积为3 741.86 hm²,占比16.56%,互花米草斑块表现为点源和边界源扩散,侵占土著植物群落生态位,对盐城湿地珍禽国家级自然保护区生态平衡造成巨大威胁。本文依托于GEE云平台,联合植被物候特征和机器学习算法,综合利用多源遥感数据,能够准确、快速、高效地提取滨海湿地互花米草信息。

关键词: GEE, 互花米草, 植被物候特征, J-M距离, 机器学习

Abstract: The invasion of alien species threatens biodiversity and destroys ecosystem structure and function. As the only coastal salt marsh plant in the list of the first 16 invasive alien species in China, the rapid and accurate identification of Spartina alterniflora (S. alterniflora) is of great significance for the sustainable development and management of coastal wetlands. Based on time-series Sentinel-2 images on the GEE, HANTS algorithm is used to fit the NDVI time-series curves, then J-M distance is used to preferentially select the key phenological periods of the S. alterniflora. Sentinel-1, Sentinel-2, and DEM datasets during the key phenological periods are integrated to construct spectral, radar, topographic, and texture features. On this basis, four machine learning methods: SVM, CART, RF and GTB are applied to extract S. alterniflora in Yancheng coastal wetlands. The results show that: ①the key phenology extracted by HANTS algorithm and J-M distance optimization for S. alterniflora identification are maturity and early senescence (October—November), and the discrimination of S. alterniflora from native plants in the key phenology is significantly improved; ② 4 classifiers are trained based on multi-source features of the key phenology, the F1-score of S. alterniflora classification resulted from SVM, CART, RF and GTB classifiers are 0.95, 0.93, 0.97 and 0.95, respectively, and RF had the best classification result; ③The existing area of S. alterniflora in the core area of Yancheng Wetland Rare Bird National Nature Reserve (YNNR) is 3 741.86 hm², accounting for 16.56%. The patches of S. alterniflora show point-source and community boundary-source diffusion, which occupy the ecological niche of native plant communities and threaten the ecological balance of YNNR. Based on the GEE cloud platform, combined with vegetation phenology characteristics and machine learning algorithms, this study utilized multi-source remote sensing data to extract S. alterniflora information in coastal wetlands accurately, rapidly, and efficiently.

Key words: Google Earth Engine, Spartina alterniflora, vegetation phenological characteristics, J-M distance, machine learning

中图分类号:

P237

刘明月, 郑浩, 陈星彤, 杨晓芜, 宋敬茹, 张永彬, 满卫东. GEE支持下联合植被物候特征与机器学习的入侵植物互花米草提取[J]. 测绘通报, 2023, 0(6): 36-43.

LIU Mingyue, ZHENG Hao, CHEN Xingtong, YANG Xiaowu, SONG Jingru, ZHANG Yongbin, MAN Weidong. Extraction of invasive plant Spartina alterniflora by combining vegetation phenological characteristics and machine learning supported by GEE[J]. Bulletin of Surveying and Mapping, 2023, 0(6): 36-43.

参考文献

[1] MÜLLEROVÁ J,BRŮNA J,BARTALOŠ T,et al. Timing is important:unmanned aircraft vs. satellite imagery in plant invasion monitoring[J]. Frontiers in Plant Science,2017,8:887.
[2] 高抒,杜永芬,谢文静,等. 苏沪浙闽海岸互花米草盐沼的环境-生态动力过程研究进展[J]. 中国科学(地球科学),2014,44(11):2339-2357.
[3] 智超,吴文挺,苏华. 潮汐和植被物候影响下的潮间带湿地遥感提取[J]. 遥感学报,2022,26(2):373-385
[4] LIU Mingyue,LI Huiying,LI Lin,et al. Monitoring the invasion of spartina alterniflora using multi-source high-resolution imagery in the Zhangjiang Estuary,China[J]. Remote Sensing,2017,9(6):539.
[5] BRADLEY B A. Remote detection of invasive plants:a review of spectral,textural and phenological approaches[J]. Biological Invasions,2014,16(7):1411-1425.
[6] WANG Jie. Mapping the dynamics of eastern redcedar encroachment into grasslands during 1984-2010 through PALSAR and time series Landsat images[J]. Remote Sensing of Environment,2017,190:233-246.
[7] LIU Jinxiu,HEISKANEN J,AYNEKULU E,et al. Land cover characterization in west sudanian savannas using seasonal features from annual landsat time series[J]. Remote Sensing,2016,8(5):365.
[8] LIU Xiang,LIU Huiyu,DATTA P,et al. Mapping an invasive plant spartina alterniflora by combining an ensemble one-class classification algorithm with a phenological NDVI time-series analysis approach in middle coast of Jiangsu,China[J]. Remote Sensing,2020,12(24):4010.
[9] TIAN Jinyan.Development of spectral-phenological features for deep learning to understand Spartina alterniflora invasion[J].Remote Sensing of Environment,2020,242:111745.
[10] 刘瑞清,李加林,孙超,等. 基于Sentinel-2遥感时间序列植被物候特征的盐城滨海湿地植被分类[J]. 地理学报,2021,76(7):1680-1692.
[11] 赵欣怡,田波,牛莹,等. Sentinel-1时序后向散射特征的海岸带盐沼植被分类:以长江口为例[J]. 遥感学报,2022,26(4):672-682.
[12] GULÁCSI A,KOVÁCS F.Sentinel-1-imagery-based high-resolution water cover detection on wetlands,aided by google earth engine[J]. Remote Sensing,2020,12(10):1614.
[13] SLAGTER B. Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data:a case study in the St. Lucia wetlands,South Africa[J]. International Journal of Applied Earth Observation and Geoinformation,2020,86:102009.
[14] MAXWELL A E,WARNER T A,FANG Fang. Implementation of machine-learning classification in remote sensing:an applied review[J]. International Journal of Remote Sensing,2018,39(9):2784-2817.
[15] LIU Mingyue,MAO Dehua,WANG Zongming,et al. Rapid invasion of Spartina alterniflora in the coastal zone of mainland China:new observations from landsat OLI images[J]. Remote Sensing,2018,10(12):1933.
[16] 董迪,曾纪胜,魏征,等. 联合星载光学和SAR影像的漳江口红树林与互花米草遥感监测[J]. 热带海洋学报,2020,39(2):107-117.
[17] GORELICK Noel.Google earth engine:planetary-scale geospatial analysis for everyone[J]. Remote Sensing of Environment,2017,202:18-27.
[18] ZHOU Jie. Reconstruction of global MODIS NDVI time series:performance of Harmonic A Nalysis of Time Series (HANTS)[J]. Remote Sensing of Environment,2015,163:217-228.
[19] TOLPEKIN V A,STEIN A. Quantification of the effects of land-cover-class spectral separability on the accuracy of Markov-random-field-based superresolution mapping[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(9):3283-3297.
[20] SCHMTDT K S, SKIDMCRE A K.Spectral discrimination of vegetation types in a coastal wetland[J]. Remote Sensing of Environment,2003,85(1):92-108.
[21] HUANG C,DAVIS L S,TOWNSHEND J R G. An assessment of support vector machines for land cover classification[J]. International Journal of Remote Sensing,2002,23(4):725-749.
[22] SHAO Yang. Comparison of support vector machine,neural network,and CART algorithms for the land-cover classification using limited training data points[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2012,70:78-87.
[23] 宁晓刚,常文涛,王浩,等. 联合GEE与多源遥感数据的黑龙江流域沼泽湿地信息提取[J]. 遥感学报,2022,26(2):386-396.
[24] 邓自发,安树青,智颖飙,等. 外来种互花米草入侵模式与爆发机制[J]. 生态学报,2006,26(8):2678-2686.

GEE支持下联合植被物候特征与机器学习的入侵植物互花米草提取

Extraction of invasive plant Spartina alterniflora by combining vegetation phenological characteristics and machine learning supported by GEE

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李鹏, 周虹利, 林是聪, 王厚杰, 李振洪. 海洋塑料垃圾卫星遥感探测方法[J]. 测绘通报, 2023, 0(6): 20-26.
[2]	奥勇, 李红丽, 张文娟, 秦梦. 基于XGBoost算法的近紫外通道地表反射率模拟[J]. 测绘通报, 2023, 0(6): 68-74,103.
[3]	李振今, 王志勇, 叶凯乐, 刘晓彤, 田康. 联合时间序列相干性和后向散射系数的黄河三角洲湿地分类[J]. 测绘通报, 2023, 0(2): 52-57,71.
[4]	孔瑞瑶, 谢涛, 马明, 孔瑞林. CatBoost模型在水深反演中的应用[J]. 测绘通报, 2022, 0(7): 33-37.
[5]	温雨笑, 吕杰, 马庆勋, 张鹏, 徐汝岭. 高光谱和LiDAR联合反演森林生物量研究[J]. 测绘通报, 2022, 0(7): 38-42.
[6]	张驰, 白志辉, 李亮, 陈冉丽, 吴侃. 利用三维激光扫描技术监测矿区桥梁结构形变[J]. 测绘通报, 2022, 0(4): 122-129.
[7]	王刚, 丁华祥. Sentinel-2A数据支持下的雷州半岛植被类型识别[J]. 测绘通报, 2022, 0(3): 76-82.
[8]	吕蓓茹, 彭玲, 李樵民. 顾及样本敏感性的滑坡易发性评价[J]. 测绘通报, 2022, 0(11): 20-25.
[9]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[10]	叶烨星, 杨飞. 基于介数中心性的交通拥堵指数计算[J]. 测绘通报, 2021, 0(5): 86-90.
[11]	张鹏, 马庆勋, 吕杰, 季金亮, 李紫微. 机器学习算法在森林地上生物量估算中的应用[J]. 测绘通报, 2021, 0(12): 28-32.
[12]	陈伟, 刘湘媛, 曾圣, 张华平, 毛志芳. 基于GEE的地表覆盖与气候状态关联研究[J]. 测绘通报, 2021, 0(12): 99-104.
[13]	夏汉庸, 尹和军, 徐教煌, 王嘉伟, 黄毅. 基于机器学习的多施工参数盾构施工姿态预测[J]. 测绘通报, 2021, 0(1): 157-160,164.
[14]	王晓静, 唐超, 杨晓飞. 激光点云在地铁盾构隧道病害诊断中的应用[J]. 测绘通报, 2020, 0(9): 33-37.
[15]	邵亚奎, 王蕾, 朱长明, 方晖, 张新, 黄端, 陶莉. GEE云平台支持下的西天山森林遥感监测与时空变化分析[J]. 测绘通报, 2020, 0(8): 13-17.